sft-zephyr-7b-beta-v4

This model is a fine-tuned version of hllj/zephyr-7b-beta-vi-math on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4249

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3484	0.52	1000	0.4761
0.2518	1.04	2000	0.4363
0.2313	1.56	3000	0.4282

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0
• Datasets 2.15.0
• Tokenizers 0.15.0